Object Detection Using Strongly-Supervised Deformable Part Models

Hossein Azizpour 1 Ivan Laptev 2
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Deformable part-based models [1, 2] achieve state-of-the-art performance for object detection, but rely on heuristic initialization during training due to the optimization of non-convex cost function. This paper investigates limitations of such an initialization and extends earlier methods using additional supervision. We explore strong supervision in terms of annotated object parts and use it to (i) improve model initialization, (ii) optimize model structure, and (iii) handle partial occlusions. Our method is able to deal with sub-optimal and incomplete annotations of object parts and is shown to benefit from semi-supervised learning setups where part-level annotation is provided for a fraction of positive examples only. Experimental results are reported for the detection of six animal classes in PASCAL VOC 2007 and 2010 datasets. We demonstrate significant improvements in detection performance compared to the LSVM [1] and the Poselet [3] object detectors.
Type de document :
Communication dans un congrès
Andrew Fitzgibbon and Svetlana Lazebnik and Pietro Perona and Yoichi Sato and Cordelia Schmid. ECCV 2012 - European Conference on Computer Vision, Oct 2012, Florence, Italy. Springer, pp.836-849, 2012, LNCS - Lecture Notes in Computer Science. 〈10.1007/978-3-642-33718-5_60〉
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01063338
Contributeur : Suha Kwak <>
Soumis le : jeudi 11 septembre 2014 - 18:16:24
Dernière modification le : mardi 17 avril 2018 - 11:26:21
Document(s) archivé(s) le : vendredi 12 décembre 2014 - 10:58:06

Fichier

ha_eccv12.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Hossein Azizpour, Ivan Laptev. Object Detection Using Strongly-Supervised Deformable Part Models. Andrew Fitzgibbon and Svetlana Lazebnik and Pietro Perona and Yoichi Sato and Cordelia Schmid. ECCV 2012 - European Conference on Computer Vision, Oct 2012, Florence, Italy. Springer, pp.836-849, 2012, LNCS - Lecture Notes in Computer Science. 〈10.1007/978-3-642-33718-5_60〉. 〈hal-01063338〉

Partager

Métriques

Consultations de la notice

290

Téléchargements de fichiers

565